Abstract: This invention describes a high-performance, log-structured implementation of a RAID subsystem that can be efficiently implemented in software. The methods described in this invention are extraordinarily well suited for software-based RAID 5 systems. In one embodiment, the disk storage subsystems receiving a request to write data. Thereafter, the write operation is appended to a first log to identify a storage location of data written to the disk subsystem, wherein the first log consists of a sequence of segments, the segments consist of a sequence of variable length stripes, a length of a stripe varies based on a quantity of disks addressed by a stripe. In response to adding a disk to the disk storage subsystem, increasing a length of the stripes and increasing a number of disks available for striping data. Alternatively, in response to a disk failing within the disk storage subsystem or a disk being removed from the disk storage system, narrowing a length of the stripes.

Abstract: This invention describes a high-performance, log-structured implementation of a RAID subsystem that can be efficiently implemented in software. The methods described here allow the RAID subsystem to achieve high performance without using specialized hardware such as non-volatile memory or hardware XOR/DMA engines. Furthermore, the RAID implementation described here is well suited for supporting many functions required for advanced storage virtualization such as virtual disks, graceful addition and removal of disks, tolerating multi-disk failures, and snapshots.